Machine learning models are poised to make a transformative impact on chemical sciences
by dramatically accelerating computational algorithms and amplifying insights available from …

Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

The two fields of machine learning and graphical causality arose and are developed
separately. However, there is, now, cross-pollination and increasing interest in both fields to …

This paper introduces a new model to learn graph neural networks equivariant to rotations,
translations, reflections and permutations called E (n)-Equivariant Graph Neural Networks …

Graphs are widely used as a popular representation of the network structure of connected
data. Graph data can be found in a broad spectrum of application domains such as social …

Learning object-centric representations of complex scenes is a promising step towards
enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep …

Abstract 'Intuitive physics' enables our pragmatic engagement with the physical world and
forms a key component of 'common sense'aspects of thought. Current artificial intelligence …

Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …

We study how neural networks trained by gradient descent extrapolate, ie, what they learn
outside the support of the training distribution. Previous works report mixed empirical results …

Even though neural networks enjoy widespread use, they still struggle to learn the basic
laws of physics. How might we endow them with better inductive biases? In this paper, we …